A5101568335- Remote Sensing in Agriculture
- Spectroscopy and Chemometric Analyses
- Smart Agriculture and AI
- Environmental Changes in China
- Leaf Properties and Growth Measurement
- Remote Sensing and Land Use
- Visual Attention and Saliency Detection
- Advanced Neural Network Applications
- Water Quality Monitoring and Analysis
- Remote-Sensing Image Classification
- Advanced Image and Video Retrieval Techniques
Wuhan University
2023-2025
Donghua University
2024-2025
Third Hospital of Hebei Medical University
2025
Hebei Medical University
2025
Gezhouba Explosive (China)
2019
Panoramic imaging is increasingly critical in UAVs and high-altitude surveillance applications. In addressing the challenges of detecting small targets within wide-area, high-resolution panoramic images, particularly issues concerning accuracy real-time performance, we have proposed an improved lightweight network model based on YOLOv8. This maintains original detection speed, while enhancing precision, reducing size parameter count by 10.6% 11.69%, respectively. It achieves a 2.9% increase...
Spectral analysis is a widely used method for monitoring photosynthetic capacity. However, vegetation indices-based linear regression exhibits insufficient utilization of spectral information, while full spectra-based traditional machine learning has limited representational capacity (partial least squares regression) or uninterpretable (convolution). In this study, we proposed deep model with enhanced interpretability based on attention and indices calculation global feature mining to...
With the challenge of increasing global carbon emissions and climate change, importance solar energy as a clean source is becoming more pronounced. Accurate radiation prediction crucial for planning operating systems. However, accurate measurement faces challenges due to high cost instruments, strict maintenance, technical complexity. Therefore, this paper proposes deep learning approach that integrates Sparrow Search Algorithm (SSA), Convolutional Neural Networks (CNN), Long Short-Term...
Deep learning methods have demonstrated state-of-the-art performance in crop type mapping, particularly with multispectral-spatial-temporal Remote Sensing (RS) images. However, few studies taken into account the temporal features separately before processing data. As is known, growth process of crops a biomass accumulation process, which involves features. In addition to extracting spatial-spectral from Convolutional Neural Network (CNN), feature extractor desired fully utilize sequential...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Accurate estimation of gross primary production (GPP) paddy rice fields is essential for understanding cropland carbon cycles, yet remains challenging due to spatial heterogeneity. In this study, we integrated high-resolution unmanned aerial vehicle (UAV) imagery into a leaf biochemical properties-based model improving GPP estimation. The key parameter, maximum carboxylation rate at the top canopy (Vcmax,025), was quantified using various information representation methods, including mean...
The maximum carboxylation rate (Vcmax) and electron transport (Jmax) of leaves are crucial for comprehending carbon cycling in farmland. Nevertheless, estimating these photosynthetic parameters precisely rapidly poses a considerable challenge. This study designed an optimal deep learning architecture that accurately extracts from hyperspectral images evaluated its stability across different crop species. Photosynthetic parameter models jointly driven by were compared with one-dimensional...